{"id":"https://openalex.org/W4412945392","doi":"https://doi.org/10.18653/v1/2025.acl-long.569","title":"User-side Model Consistency Monitoring for Open Source Large Language Models Inference Services","display_name":"User-side Model Consistency Monitoring for Open Source Large Language Models Inference Services","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945392","doi":"https://doi.org/10.18653/v1/2025.acl-long.569"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.569","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.569","pdf_url":"https://aclanthology.org/2025.acl-long.569.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.569.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119204507","display_name":"Qijun Miao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qijun Miao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010064740","display_name":"Zhixuan Fang","orcid":"https://orcid.org/0000-0001-7979-4269"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhixuan Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08884537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11610","last_page":"11622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.901199996471405,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.901199996471405,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7606692314147949},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6414793729782104},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6254342794418335},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6149616241455078},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4168005883693695},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.41046640276908875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.30449795722961426},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3023144602775574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2731896638870239},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2728918790817261},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.0987136960029602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606692314147949},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6414793729782104},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6254342794418335},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6149616241455078},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4168005883693695},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.41046640276908875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30449795722961426},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3023144602775574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2731896638870239},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2728918790817261},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0987136960029602}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.569","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.569","pdf_url":"https://aclanthology.org/2025.acl-long.569.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.569","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.569","pdf_url":"https://aclanthology.org/2025.acl-long.569.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945392.pdf","grobid_xml":"https://content.openalex.org/works/W4412945392.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W1603736412","https://openalex.org/W4304185162","https://openalex.org/W2124842464","https://openalex.org/W2382657549","https://openalex.org/W4376877853","https://openalex.org/W2061685118","https://openalex.org/W3006282800","https://openalex.org/W2462100143","https://openalex.org/W75565505"],"abstract_inverted_index":{"With":[0],"the":[1,5,97,104,124,161,166],"continuous":[2],"advancement":[3],"in":[4,73],"performance":[6],"of":[7,165],"open-source":[8],"large":[9],"language":[10],"models":[11,28],"(LLMs),":[12],"their":[13],"inference":[14],"services":[15],"have":[16],"attracted":[17],"a":[18,30,56,79,90,153],"substantial":[19],"user":[20,98],"base":[21],"by":[22,107,113,116],"offering":[23],"quality":[24],"comparable":[25],"to":[26,39,109],"closed-source":[27],"at":[29],"significantly":[31],"lower":[32],"cost.However,":[33],"it":[34],"has":[35],"also":[36],"given":[37],"rise":[38],"trust":[40],"issues":[41],"regarding":[42],"model":[43,93,118],"consistency":[44,94],"between":[45],"users":[46,68],"and":[47,66,143,163],"third-party":[48],"service":[49,51],"providers.Specifically,":[50],"providers":[52],"can":[53],"effortlessly":[54],"degrade":[55],"model's":[57],"parameter":[58],"scale":[59],"or":[60],"precision":[61],"for":[62,82,92],"more":[63],"margin":[64],"profits,":[65],"although":[67],"may":[69],"perceptibly":[70],"experience":[71],"differences":[72],"text":[74],"quality,":[75],"they":[76],"often":[77],"lack":[78],"reliable":[80],"method":[81,126],"concrete":[83],"monitoring.To":[84],"address":[85],"this":[86],"problem,":[87],"we":[88,121],"propose":[89],"paradigm":[91],"monitoring":[95],"on":[96,103,129,134,152],"side.It":[99],"constructs":[100],"metrics":[101],"based":[102],"logits":[105],"produced":[106],"LLMs":[108,138],"differentiate":[110],"sequences":[111],"generated":[112],"degraded":[114],"models.Furthermore,":[115],"leveraging":[117],"offloading":[119],"techniques,":[120],"demonstrate":[122],"that":[123],"proposed":[125,167],"is":[127],"implementable":[128],"consumer-grade":[130],"devices.Metric":[131],"evaluations":[132],"conducted":[133],"three":[135],"widely":[136],"used":[137],"series":[139],"(OPT,":[140],"Llama":[141],"3.1":[142],"Qwen":[144],"2.5)":[145],"along":[146],"with":[147],"system":[148],"prototype":[149],"efficiency":[150],"tests":[151],"consumer":[154],"device":[155],"(RTX":[156],"3080":[157],"TI)":[158],"confirm":[159],"both":[160],"effectiveness":[162],"feasibility":[164],"approach.":[168]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}